phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-25 18:54:30 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix(litellm/caching/caching_handler.py): fix kwargs[litellm_params][preset_cache_key] not being propogated up the call stack during a cache hit, resulting in the x-litellm-cache-key header not being returned

Browse source
This commit is contained in:
michael rodriguez 2025-02-25 22:04:47 -05:00
parent f9cee4c46b
commit 5bcb50d4a2
1 changed files with 9 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

11
litellm/caching/caching_handler.py
View file

@ -476,14 +476,17 @@ class LLMCachingHandler:
"""
if litellm.cache is None:
return None
new_kwargs = kwargs.copy()
new_kwargs = kwargs
new_kwargs.update(
convert_args_to_kwargs(
self.original_function,
args,
)
)
if "litellm_params" not in new_kwargs:
new_kwargs["litellm_params"] = {}
cached_result: Optional[Any] = None
if call_type == CallTypes.aembedding.value and isinstance(
new_kwargs["input"], list
@ -503,6 +506,10 @@ class LLMCachingHandler:
else:
if litellm.cache._supports_async() is True:
cached_result = await litellm.cache.async_get_cache(**new_kwargs)
if cached_result == None and list(new_kwargs["litellm_params"].keys()) == ["preset_cache_key"]:
del new_kwargs["litellm_params"]
else: # for s3 caching. [NOT RECOMMENDED IN PROD - this will slow down responses since boto3 is sync]
cached_result = litellm.cache.get_cache(**new_kwargs)
return cached_result